
# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask


# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")


nltk.download('all')

[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all

True


# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_tvshows = pd.read_csv(path + 'otttvshows.csv')
 
df_tvshows.head()


# profile = ProfileReport(df_tvshows)
# profile


def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()


data_investigate(df_tvshows)

No of Rows :  5432
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                1954
IMDb                556
Rotten Tomatoes    4194
Directors          5158
Cast                486
Genres              323
Country             549
Language            638
Plotline           2493
Runtime            1410
Seasons             679
dtype: int64
**************************************************
Missing vaules %age wise :

ID                  0.000000
Title               0.000000
Year                0.000000
Age                35.972018
IMDb               10.235641
Rotten Tomatoes    77.209131
Directors          94.955817
Cast                8.946981
Genres              5.946244
Country            10.106775
Language           11.745214
Plotline           45.894698
Runtime            25.957290
Kind                0.000000
Seasons            12.500000
Netflix             0.000000
Hulu                0.000000
Prime Video         0.000000
Disney+             0.000000
Type                0.000000
dtype: float64
**************************************************
Pictorial Representation :


# ID
# df_tvshows = df_tvshows.drop(['ID'], axis = 1)
 
# Age
df_tvshows.loc[df_tvshows['Age'].isnull() & df_tvshows['Disney+'] == 1, "Age"] = '13'
# df_tvshows.fillna({'Age' : 18}, inplace = True)
df_tvshows.fillna({'Age' : 'NR'}, inplace = True)
df_tvshows['Age'].replace({'all': '0'}, inplace = True)
df_tvshows['Age'].replace({'7+': '7'}, inplace = True)
df_tvshows['Age'].replace({'13+': '13'}, inplace = True)
df_tvshows['Age'].replace({'16+': '16'}, inplace = True)
df_tvshows['Age'].replace({'18+': '18'}, inplace = True)
# df_tvshows['Age'] = df_tvshows['Age'].astype(int)
 
# IMDb
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].mean()}, inplace = True)
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].median()}, inplace = True)
df_tvshows.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].astype(int)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].mean()}, inplace = True)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].median()}, inplace = True)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'].astype(int)
df_tvshows.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Casts
# df_tvshows = df_tvshows.drop(['Casts'], axis = 1)
df_tvshows.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_tvshows.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_tvshows.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_tvshows.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_tvshows.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_tvshows.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_tvshows.fillna({'Runtime' : df_tvshows['Runtime'].mean()}, inplace = True)
# df_tvshows['Runtime'] = df_tvshows['Runtime'].astype(int)
df_tvshows.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_tvshows.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_tvshows.fillna({'Type': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Type'], axis = 1)
 
# Seasons
# df_tvshows.fillna({'Seasons': 1}, inplace = True)
df_tvshows.fillna({'Seasons': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Seasons'], axis = 1)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
# df_tvshows.fillna({'Seasons' : df_tvshows['Seasons'].mean()}, inplace = True)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
 
# Service Provider
df_tvshows['Service Provider'] = df_tvshows.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_tvshows.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_tvshows.dropna(how = 'any', inplace = True)
df_tvshows.drop_duplicates(inplace = True)


data_investigate(df_tvshows)

No of Rows :  5432
No of Coloums :  21
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Seasons             object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Seasons             0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation :


df_tvshows.head()


df_tvshows.describe()


df_tvshows.corr()


# df_tvshows.sort_values('Year', ascending = True)
# df_tvshows.sort_values('IMDb', ascending = False)


# df_tvshows.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_otttvshows.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_tvshows = pd.read_csv(path + 'updated_otttvshows.csv')
 
# udf_tvshows


# df_netflix_tvshows = df_tvshows.loc[(df_tvshows['Netflix'] > 0)]
# df_hulu_tvshows = df_tvshows.loc[(df_tvshows['Hulu'] > 0)]
# df_prime_video_tvshows = df_tvshows.loc[(df_tvshows['Prime Video'] > 0)]
# df_disney_tvshows = df_tvshows.loc[(df_tvshows['Disney+'] > 0)]


df_netflix_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 1) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_hulu_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 1) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_prime_video_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 1 ) & (df_tvshows['Disney+'] == 0)]
df_disney_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 1)]


df_tvshows_casts = df_tvshows.copy()


df_tvshows_casts.drop(df_tvshows_casts.loc[df_tvshows_casts['Cast'] == "NA"].index, inplace = True)
# df_tvshows_casts = df_tvshows_casts[df_tvshows_casts.Cast != "NA"]
# df_tvshows_casts['Cast'] = df_tvshows_casts['Cast'].astype(str)


df_tvshows_count_casts = df_tvshows_casts.copy()


df_tvshows_cast = df_tvshows_casts.copy()


# Create casts dict where key=name and value = number of casts
 
casts = {}
 
for i in df_tvshows_count_casts['Cast'].dropna():
    if i != "NA":
        #print(i,len(i.split(',')))
        casts[i] = len(i.split(','))
    else:
        casts[i] = 0
    
# Add this information to our dataframe as a new column
 
df_tvshows_count_casts['Number of Casts'] = df_tvshows_count_casts['Cast'].map(casts).astype(int)


df_tvshows_mixed_casts = df_tvshows_count_casts.copy()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_casts_tvshows = df_tvshows_count_casts.loc[df_tvshows_count_casts['Netflix'] == 1]
hulu_casts_tvshows = df_tvshows_count_casts.loc[df_tvshows_count_casts['Hulu'] == 1]
prime_video_casts_tvshows = df_tvshows_count_casts.loc[df_tvshows_count_casts['Prime Video'] == 1]
disney_casts_tvshows = df_tvshows_count_casts.loc[df_tvshows_count_casts['Disney+'] == 1]


plt.figure(figsize = (10, 10))
corr = df_tvshows_count_casts.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, alleast annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()

<Figure size 720x720 with 0 Axes>


df_casts_most_tvshows = df_tvshows_count_casts.sort_values(by = 'Number of Casts', ascending = False).reset_index()
df_casts_most_tvshows = df_casts_most_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_count_casts['Number of Casts'] == (df_tvshows_count_casts['Number of Casts'].max()))
# df_casts_most_tvshows = df_tvshows_count_casts[filter]
 
# mostest_rated_tvshows = df_tvshows_count_casts.loc[df_tvshows_count_casts['Number of Casts'].idxmax()]
 
print('\nTV Shows with Highest Ever Number of Casts are : \n')
df_casts_most_tvshows.head(5)

TV Shows with Highest Ever Number of Casts are :


fig = px.bar(y = df_casts_most_tvshows['Title'][:15],
             x = df_casts_most_tvshows['Number of Casts'][:15], 
             color = df_casts_most_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Highest Number of Casts : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_casts_least_tvshows = df_tvshows_count_casts.sort_values(by = 'Number of Casts', ascending = True).reset_index()
df_casts_least_tvshows = df_casts_least_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_count_casts['Number of Casts'] == (df_tvshows_count_casts['Number of Casts'].min()))
# df_casts_least_tvshows = df_tvshows_count_casts[filter]

print('\nTV Shows with Lowest Ever Number of Casts are : \n')
df_casts_least_tvshows.head(5)

TV Shows with Lowest Ever Number of Casts are :


fig = px.bar(y = df_casts_least_tvshows['Title'][:15],
             x = df_casts_least_tvshows['Number of Casts'][:15], 
             color = df_casts_least_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Lowest Number of Casts : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_tvshows_count_casts['Number of Casts'].unique().shape[0]}' unique Number of Casts s were Given, They were Like this,\n
      
      {df_tvshows_count_casts.sort_values(by = 'Number of Casts', ascending = False)['Number of Casts'].unique()}\n
 
      The Highest Number of Casts Ever Any TV Show Got is '{df_casts_most_tvshows['Title'][0]}' : '{df_casts_most_tvshows['Number of Casts'].max()}'\n
 
      The Lowest Number of Casts Ever Any TV Show Got is '{df_casts_least_tvshows['Title'][0]}' : '{df_casts_least_tvshows['Number of Casts'].min()}'\n
      ''')

      Total '51' unique Number of Casts s were Given, They were Like this,

      
      [53 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32 31 30 29 28
 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4
  3  2  1]

 
      The Highest Number of Casts Ever Any TV Show Got is 'The French Gun' : '53'

 
      The Lowest Number of Casts Ever Any TV Show Got is 'Struggle Meals' : '1'


netflix_casts_most_tvshows = df_casts_most_tvshows.loc[df_casts_most_tvshows['Netflix']==1].reset_index()
netflix_casts_most_tvshows = netflix_casts_most_tvshows.drop(['index'], axis = 1)
 
netflix_casts_least_tvshows = df_casts_least_tvshows.loc[df_casts_least_tvshows['Netflix']==1].reset_index()
netflix_casts_least_tvshows = netflix_casts_least_tvshows.drop(['index'], axis = 1)
 
netflix_casts_most_tvshows.head(5)


fig = px.bar(y = netflix_casts_most_tvshows['Title'][:15],
             x = netflix_casts_most_tvshows['Number of Casts'][:15], 
             color = netflix_casts_most_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Highest Number of Casts : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = netflix_casts_least_tvshows['Title'][:15],
             x = netflix_casts_least_tvshows['Number of Casts'][:15], 
             color = netflix_casts_least_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Lowest Number of Casts : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


hulu_casts_most_tvshows = df_casts_most_tvshows.loc[df_casts_most_tvshows['Hulu']==1].reset_index()
hulu_casts_most_tvshows = hulu_casts_most_tvshows.drop(['index'], axis = 1)
 
hulu_casts_least_tvshows = df_casts_least_tvshows.loc[df_casts_least_tvshows['Hulu']==1].reset_index()
hulu_casts_least_tvshows = hulu_casts_least_tvshows.drop(['index'], axis = 1)
 
hulu_casts_most_tvshows.head(5)


fig = px.bar(y = hulu_casts_most_tvshows['Title'][:15],
             x = hulu_casts_most_tvshows['Number of Casts'][:15], 
             color = hulu_casts_most_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Highest Number of Casts : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = hulu_casts_least_tvshows['Title'][:15],
             x = hulu_casts_least_tvshows['Number of Casts'][:15], 
             color = hulu_casts_least_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Lowest Number of Casts : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


prime_video_casts_most_tvshows = df_casts_most_tvshows.loc[df_casts_most_tvshows['Prime Video']==1].reset_index()
prime_video_casts_most_tvshows = prime_video_casts_most_tvshows.drop(['index'], axis = 1)
 
prime_video_casts_least_tvshows = df_casts_least_tvshows.loc[df_casts_least_tvshows['Prime Video']==1].reset_index()
prime_video_casts_least_tvshows = prime_video_casts_least_tvshows.drop(['index'], axis = 1)
 
prime_video_casts_most_tvshows.head(5)


fig = px.bar(y = prime_video_casts_most_tvshows['Title'][:15],
             x = prime_video_casts_most_tvshows['Number of Casts'][:15], 
             color = prime_video_casts_most_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Highest Number of Casts : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = prime_video_casts_least_tvshows['Title'][:15],
             x = prime_video_casts_least_tvshows['Number of Casts'][:15], 
             color = prime_video_casts_least_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Lowest Number of Casts : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


disney_casts_most_tvshows = df_casts_most_tvshows.loc[df_casts_most_tvshows['Disney+']==1].reset_index()
disney_casts_most_tvshows = disney_casts_most_tvshows.drop(['index'], axis = 1)
 
disney_casts_least_tvshows = df_casts_least_tvshows.loc[df_casts_least_tvshows['Disney+']==1].reset_index()
disney_casts_least_tvshows = disney_casts_least_tvshows.drop(['index'], axis = 1)
 
disney_casts_most_tvshows.head(5)


fig = px.bar(y = disney_casts_most_tvshows['Title'][:15],
             x = disney_casts_most_tvshows['Number of Casts'][:15], 
             color = disney_casts_most_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Highest Number of Casts : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = disney_casts_least_tvshows['Title'][:15],
             x = disney_casts_least_tvshows['Number of Casts'][:15], 
             color = disney_casts_least_tvshows['Number of Casts'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Casts'},
             title  = 'TV Shows with Lowest Number of Casts : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      The TV Show with Highest Number of Casts Ever Got is '{df_casts_most_tvshows['Title'][0]}' : '{df_casts_most_tvshows['Number of Casts'].max()}'\n
      The TV Show with Lowest Number of Casts Ever Got is '{df_casts_least_tvshows['Title'][0]}' : '{df_casts_least_tvshows['Number of Casts'].min()}'\n
      
      The TV Show with Highest Number of Casts on 'Netflix' is '{netflix_casts_most_tvshows['Title'][0]}' : '{netflix_casts_most_tvshows['Number of Casts'].max()}'\n
      The TV Show with Lowest Number of Casts on 'Netflix' is '{netflix_casts_least_tvshows['Title'][0]}' : '{netflix_casts_least_tvshows['Number of Casts'].min()}'\n
      
      The TV Show with Highest Number of Casts on 'Hulu' is '{hulu_casts_most_tvshows['Title'][0]}' : '{hulu_casts_most_tvshows['Number of Casts'].max()}'\n
      The TV Show with Lowest Number of Casts on 'Hulu' is '{hulu_casts_least_tvshows['Title'][0]}' : '{hulu_casts_least_tvshows['Number of Casts'].min()}'\n
      
      The TV Show with Highest Number of Casts on 'Prime Video' is '{prime_video_casts_most_tvshows['Title'][0]}' : '{prime_video_casts_most_tvshows['Number of Casts'].max()}'\n
      The TV Show with Lowest Number of Casts on 'Prime Video' is '{prime_video_casts_least_tvshows['Title'][0]}' : '{prime_video_casts_least_tvshows['Number of Casts'].min()}'\n
      
      The TV Show with Highest Number of Casts on 'Disney+' is '{disney_casts_most_tvshows['Title'][0]}' : '{disney_casts_most_tvshows['Number of Casts'].max()}'\n
      The TV Show with Lowest Number of Casts on 'Disney+' is '{disney_casts_least_tvshows['Title'][0]}' : '{disney_casts_least_tvshows['Number of Casts'].min()}'\n 
      ''')

      The TV Show with Highest Number of Casts Ever Got is 'The French Gun' : '53'

      The TV Show with Lowest Number of Casts Ever Got is 'Struggle Meals' : '1'

      
      The TV Show with Highest Number of Casts on 'Netflix' is 'Snowpiercer' : '50'

      The TV Show with Lowest Number of Casts on 'Netflix' is 'Everyday Miracles: The Genius of Sofas, Stockings and Scanners' : '1'

      
      The TV Show with Highest Number of Casts on 'Hulu' is 'Dirty Sexy Money' : '50'

      The TV Show with Lowest Number of Casts on 'Hulu' is 'Struggle Meals' : '1'

      
      The TV Show with Highest Number of Casts on 'Prime Video' is 'The French Gun' : '53'

      The TV Show with Lowest Number of Casts on 'Prime Video' is 'Struggle Meals' : '1'

      
      The TV Show with Highest Number of Casts on 'Disney+' is 'K.C. Undercover' : '50'

      The TV Show with Lowest Number of Casts on 'Disney+' is 'Disney Gallery / Star Wars: The Mandalorian' : '1'


print(f'''
      Accross All Platforms the Average Number of Casts is '{round(df_tvshows_count_casts['Number of Casts'].mean(), ndigits = 2)}'\n
      The Average Number of Casts on 'Netflix' is '{round(netflix_casts_tvshows['Number of Casts'].mean(), ndigits = 2)}'\n
      The Average Number of Casts on 'Hulu' is '{round(hulu_casts_tvshows['Number of Casts'].mean(), ndigits = 2)}'\n
      The Average Number of Casts on 'Prime Video' is '{round(prime_video_casts_tvshows['Number of Casts'].mean(), ndigits = 2)}'\n
      The Average Number of Casts on 'Disney+' is '{round(disney_casts_tvshows['Number of Casts'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Number of Casts is '34.01'

      The Average Number of Casts on 'Netflix' is '33.59'

      The Average Number of Casts on 'Hulu' is '40.19'

      The Average Number of Casts on 'Prime Video' is '30.41'

      The Average Number of Casts on 'Disney+' is '35.12'


print(f'''
      Accross All Platforms Total Count of Cast is '{df_tvshows_count_casts['Number of Casts'].max()}'\n
      Total Count of Cast on 'Netflix' is '{netflix_casts_tvshows['Number of Casts'].max()}'\n
      Total Count of Cast on 'Hulu' is '{hulu_casts_tvshows['Number of Casts'].max()}'\n
      Total Count of Cast on 'Prime Video' is '{prime_video_casts_tvshows['Number of Casts'].max()}'\n
      Total Count of Cast on 'Disney+' is '{disney_casts_tvshows['Number of Casts'].max()}'\n 
      ''')

      Accross All Platforms Total Count of Cast is '53'

      Total Count of Cast on 'Netflix' is '50'

      Total Count of Cast on 'Hulu' is '50'

      Total Count of Cast on 'Prime Video' is '53'

      Total Count of Cast on 'Disney+' is '50'


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_tvshows_count_casts['Number of Casts'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_tvshows_count_casts['Number of Casts'], ax = ax[1])
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Number of Casts s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_casts_tvshows['Number of Casts'], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_casts_tvshows['Number of Casts'], color = 'red', legend = True, kde = True)
sns.histplot(hulu_casts_tvshows['Number of Casts'], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_casts_tvshows['Number of Casts'], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


df_lan = df_tvshows_cast['Cast'].str.split(',').apply(pd.Series).stack()
del df_tvshows_cast['Cast']
df_lan.index = df_lan.index.droplevel(-1)
df_lan.name = 'Cast'
df_tvshows_cast = df_tvshows_cast.join(df_lan)
df_tvshows_cast.drop_duplicates(inplace = True)


df_tvshows_cast.head(5)


cast_count = df_tvshows_cast.groupby('Cast')['Title'].count()
cast_tvshows = df_tvshows_cast.groupby('Cast')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
cast_data_tvshows = pd.concat([cast_count, cast_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count'})
cast_data_tvshows = cast_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)


# Cast with TV Shows Counts - All Platforms Combined
cast_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)[:10]


fig = px.bar(x = cast_data_tvshows['Cast'][:50],
             y = cast_data_tvshows['TV Shows Count'][:50], 
             color = cast_data_tvshows['TV Shows Count'][:50],
             color_continuous_scale = 'Teal_r', 
             labels = { 'x' : 'Cast', 'y' : 'TV Shows Count'},
             title  = 'Major Casts : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_cast_high_tvshows = cast_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_cast_high_tvshows = df_cast_high_tvshows.drop(['index'], axis = 1)
# filter = (cast_data_tvshows['TV Shows Count'] == (cast_data_tvshows['TV Shows Count'].max()))
# df_cast_high_tvshows = cast_data_tvshows[filter]
 
# highest_rated_tvshows = cast_data_tvshows.loc[cast_data_tvshows['TV Shows Count'].idxmax()]
 
print('\nCast with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_cast_high_tvshows.head(5)

Cast with Highest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_cast_high_tvshows['Cast'][:15],
             x = df_cast_high_tvshows['TV Shows Count'][:15], 
             color = df_cast_high_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Highest TV Shows : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_cast_low_tvshows = cast_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_cast_low_tvshows = df_cast_low_tvshows.drop(['index'], axis = 1)
# filter = (cast_data_tvshows['TV Shows Count'] == (cast_data_tvshows['TV Shows Count'].min()))
# df_cast_low_tvshows = cast_data_tvshows[filter]

print('\nCast with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_cast_low_tvshows.head(5)

Cast with Lowest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_cast_low_tvshows['Cast'][:15],
             x = df_cast_low_tvshows['TV Shows Count'][:15], 
             color = df_cast_low_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Lowest TV Shows Count : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{cast_data_tvshows['Cast'].unique().shape[0]}' unique Cast Count s were Given, They were Like this,\n
      
      {cast_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['Cast'].unique()[:5]}\n
 
      The Highest Ever TV Shows Count Ever Any TV Show Got is '{df_cast_high_tvshows['Cast'][0]}' : '{df_cast_high_tvshows['TV Shows Count'].max()}'\n
 
      The Lowest Ever TV Shows Count Ever Any TV Show Got is '{df_cast_low_tvshows['Cast'][0]}' : '{df_cast_low_tvshows['TV Shows Count'].min()}'\n
      ''')

      Total '100452' unique Cast Count s were Given, They were Like this,

      
      ['Dee Bradley Baker' 'Grey Griffin' 'Monica Rial'
 'Kevin Michael Richardson' 'Fred Tatasciore']

 
      The Highest Ever TV Shows Count Ever Any TV Show Got is 'Dee Bradley Baker' : '94'

 
      The Lowest Ever TV Shows Count Ever Any TV Show Got is 'Pamela West' : '1'


fig = px.pie(cast_data_tvshows[:10], names = 'Cast', values = 'TV Shows Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'TV Shows Count based on Cast')
fig.show()


# netflix_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_cast_tvshows = netflix_cast_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
netflix_cast_high_tvshows = df_cast_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_cast_high_tvshows = netflix_cast_high_tvshows.drop(['index'], axis = 1)
 
netflix_cast_low_tvshows = df_cast_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_cast_low_tvshows = netflix_cast_low_tvshows.drop(['index'], axis = 1)
 
netflix_cast_high_tvshows.head(5)


fig = px.bar(x = netflix_cast_high_tvshows['Cast'][:15],
             y = netflix_cast_high_tvshows['Netflix'][:15], 
             color = netflix_cast_high_tvshows['Netflix'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Highest TV Shows : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# hulu_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_cast_tvshows = hulu_cast_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
hulu_cast_high_tvshows = df_cast_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_cast_high_tvshows = hulu_cast_high_tvshows.drop(['index'], axis = 1)
 
hulu_cast_low_tvshows = df_cast_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_cast_low_tvshows = hulu_cast_low_tvshows.drop(['index'], axis = 1)
 
hulu_cast_high_tvshows.head(5)


fig = px.bar(x = hulu_cast_high_tvshows['Cast'][:15],
             y = hulu_cast_high_tvshows['Hulu'][:15], 
             color = hulu_cast_high_tvshows['Hulu'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Highest TV Shows : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# prime_video_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_cast_tvshows = prime_video_cast_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
 
prime_video_cast_high_tvshows = df_cast_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_cast_high_tvshows = prime_video_cast_high_tvshows.drop(['index'], axis = 1)
 
prime_video_cast_low_tvshows = df_cast_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_cast_low_tvshows = prime_video_cast_low_tvshows.drop(['index'], axis = 1)
 
prime_video_cast_high_tvshows.head(5)


fig = px.bar(x = prime_video_cast_high_tvshows['Cast'][:15],
             y = prime_video_cast_high_tvshows['Prime Video'][:15], 
             color = prime_video_cast_high_tvshows['Prime Video'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Highest TV Shows : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# disney_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_cast_tvshows = disney_cast_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
 
disney_cast_high_tvshows = df_cast_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_cast_high_tvshows = disney_cast_high_tvshows.drop(['index'], axis = 1)
 
disney_cast_low_tvshows = df_cast_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_cast_low_tvshows = disney_cast_low_tvshows.drop(['index'], axis = 1)
 
disney_cast_high_tvshows.head(5)


fig = px.bar(x = disney_cast_high_tvshows['Cast'][:15],
             y = disney_cast_high_tvshows['Disney+'][:15], 
             color = disney_cast_high_tvshows['Disney+'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Cast', 'x' : 'TV Shows Count'},
             title  = 'Cast with Highest TV Shows : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(cast_data_tvshows['TV Shows Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(cast_data_tvshows['TV Shows Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_cast_tvshows = netflix_cast_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

hulu_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_cast_tvshows = hulu_cast_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

prime_video_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_cast_tvshows = prime_video_cast_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)

disney_cast_tvshows = cast_data_tvshows[cast_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_cast_tvshows = disney_cast_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Cast TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(disney_cast_tvshows['Disney+'][:50], color = 'darkblue', legend = True, kde = True)  
sns.histplot(prime_video_cast_tvshows['Prime Video'][:50], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_cast_tvshows['Netflix'][:50], color = 'red', legend = True, kde = True)
sns.histplot(hulu_cast_tvshows['Hulu'][:50], color = 'lightgreen', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Disney+', 'Prime Video', 'Netflix', 'Hulu'])
plt.show()


print(f'''
      The Cast with Highest TV Shows Count Ever Got is '{df_cast_high_tvshows['Cast'][0]}' : '{df_cast_high_tvshows['TV Shows Count'].max()}'\n
      The Cast with Lowest TV Shows Count Ever Got is '{df_cast_low_tvshows['Cast'][0]}' : '{df_cast_low_tvshows['TV Shows Count'].min()}'\n
      
      The Cast with Highest TV Shows Count on 'Netflix' is '{netflix_cast_high_tvshows['Cast'][0]}' : '{netflix_cast_high_tvshows['Netflix'].max()}'\n
      The Cast with Lowest TV Shows Count on 'Netflix' is '{netflix_cast_low_tvshows['Cast'][0]}' : '{netflix_cast_low_tvshows['Netflix'].min()}'\n
      
      The Cast with Highest TV Shows Count on 'Hulu' is '{hulu_cast_high_tvshows['Cast'][0]}' : '{hulu_cast_high_tvshows['Hulu'].max()}'\n
      The Cast with Lowest TV Shows Count on 'Hulu' is '{hulu_cast_low_tvshows['Cast'][0]}' : '{hulu_cast_low_tvshows['Hulu'].min()}'\n
      
      The Cast with Highest TV Shows Count on 'Prime Video' is '{prime_video_cast_high_tvshows['Cast'][0]}' : '{prime_video_cast_high_tvshows['Prime Video'].max()}'\n
      The Cast with Lowest TV Shows Count on 'Prime Video' is '{prime_video_cast_low_tvshows['Cast'][0]}' : '{prime_video_cast_low_tvshows['Prime Video'].min()}'\n
      
      The Cast with Highest TV Shows Count on 'Disney+' is '{disney_cast_high_tvshows['Cast'][0]}' : '{disney_cast_high_tvshows['Disney+'].max()}'\n
      The Cast with Lowest TV Shows Count on 'Disney+' is '{disney_cast_low_tvshows['Cast'][0]}' : '{disney_cast_low_tvshows['Disney+'].min()}'\n 
      ''')

      The Cast with Highest TV Shows Count Ever Got is 'Dee Bradley Baker' : '94'

      The Cast with Lowest TV Shows Count Ever Got is 'Pamela West' : '1'

      
      The Cast with Highest TV Shows Count on 'Netflix' is 'Keith Silverstein' : '35'

      The Cast with Lowest TV Shows Count on 'Netflix' is 'Hiroki Totsuka' : '0'

      
      The Cast with Highest TV Shows Count on 'Hulu' is 'Monica Rial' : '74'

      The Cast with Lowest TV Shows Count on 'Hulu' is 'Þórunn Gunnlaugsdóttir' : '0'

      
      The Cast with Highest TV Shows Count on 'Prime Video' is 'Grey Griffin' : '15'

      The Cast with Lowest TV Shows Count on 'Prime Video' is 'Þórunn Gunnlaugsdóttir' : '0'

      
      The Cast with Highest TV Shows Count on 'Disney+' is 'Dee Bradley Baker' : '38'

      The Cast with Lowest TV Shows Count on 'Disney+' is 'Hiroki Totsuka' : '0'


# Distribution of tvshows cast in each platform
plt.figure(figsize = (20, 5))
plt.title('Cast with TV Shows Count for All Platforms')
sns.violinplot(x = cast_data_tvshows['TV Shows Count'][:100], color = 'gold', legend = True, kde = True, shade = False)
plt.show()


# Distribution of Cast TV Shows Count in each platform
f1, ax1 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = netflix_cast_tvshows['Netflix'][:100], color = 'red', ax = ax1[0])
sns.violinplot(x = hulu_cast_tvshows['Hulu'][:100], color = 'lightgreen', ax = ax1[1])
 
f2, ax2 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = prime_video_cast_tvshows['Prime Video'][:100], color = 'lightblue', ax = ax2[0])
sns.violinplot(x = disney_cast_tvshows['Disney+'][:100], color = 'darkblue', ax = ax2[1])
plt.show()


print(f'''
      Accross All Platforms the Average TV Shows Count of Cast is '{round(cast_data_tvshows['TV Shows Count'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Cast on 'Netflix' is '{round(netflix_cast_tvshows['Netflix'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Cast on 'Hulu' is '{round(hulu_cast_tvshows['Hulu'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Cast on 'Prime Video' is '{round(prime_video_cast_tvshows['Prime Video'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Cast on 'Disney+' is '{round(disney_cast_tvshows['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average TV Shows Count of Cast is '1.67'

      The Average TV Shows Count of Cast on 'Netflix' is '1.35'

      The Average TV Shows Count of Cast on 'Hulu' is '1.51'

      The Average TV Shows Count of Cast on 'Prime Video' is '1.27'

      The Average TV Shows Count of Cast on 'Disney+' is '1.35'


print(f'''
      Accross All Platforms Total Count of Cast is '{cast_data_tvshows['Cast'].unique().shape[0]}'\n
      Total Count of Cast on 'Netflix' is '{netflix_cast_tvshows['Cast'].unique().shape[0]}'\n
      Total Count of Cast on 'Hulu' is '{hulu_cast_tvshows['Cast'].unique().shape[0]}'\n
      Total Count of Cast on 'Prime Video' is '{prime_video_cast_tvshows['Cast'].unique().shape[0]}'\n
      Total Count of Cast on 'Disney+' is '{disney_cast_tvshows['Cast'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Cast is '100452'

      Total Count of Cast on 'Netflix' is '44475'

      Total Count of Cast on 'Hulu' is '39921'

      Total Count of Cast on 'Prime Video' is '44367'

      Total Count of Cast on 'Disney+' is '4697'


plt.figure(figsize = (20, 5))
sns.lineplot(x = cast_data_tvshows['Cast'][:10], y = cast_data_tvshows['Netflix'][:10], color = 'red')
sns.lineplot(x = cast_data_tvshows['Cast'][:10], y = cast_data_tvshows['Hulu'][:10], color = 'lightgreen')
sns.lineplot(x = cast_data_tvshows['Cast'][:10], y = cast_data_tvshows['Prime Video'][:10], color = 'lightblue')
sns.lineplot(x = cast_data_tvshows['Cast'][:10], y = cast_data_tvshows['Disney+'][:10], color = 'darkblue')
plt.xlabel('Cast', fontsize = 20)
plt.ylabel('TV Shows Count', fontsize = 20)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_c_ax1 = sns.lineplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_c_ax2 = sns.lineplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_c_ax3 = sns.lineplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_c_ax4 = sns.lineplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_c_ax1.title.set_text(labels[0])
h_c_ax2.title.set_text(labels[1])
p_c_ax3.title.set_text(labels[2])
d_c_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_c_ax1 = sns.barplot(y = netflix_cast_tvshows['Cast'][:10], x = netflix_cast_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_c_ax2 = sns.barplot(y = hulu_cast_tvshows['Cast'][:10], x = hulu_cast_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_c_ax3 = sns.barplot(y = prime_video_cast_tvshows['Cast'][:10], x = prime_video_cast_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_c_ax4 = sns.barplot(y = disney_cast_tvshows['Cast'][:10], x = disney_cast_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_c_ax1.title.set_text(labels[0])
h_c_ax2.title.set_text(labels[1])
p_c_ax3.title.set_text(labels[2])
d_c_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Cast  TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_cast_tvshows['Netflix'][:10], color = 'red', legend = True)
sns.kdeplot(hulu_cast_tvshows['Hulu'][:10], color = 'green', legend = True)
sns.kdeplot(prime_video_cast_tvshows['Prime Video'][:10], color = 'lightblue', legend = True)
sns.kdeplot(disney_cast_tvshows['Disney+'][:10], color = 'darkblue', legend = True)                                      
                                      
# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_c_ax1 = sns.barplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_c_ax2 = sns.barplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_c_ax3 = sns.barplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_c_ax4 = sns.barplot(y = cast_data_tvshows['Cast'][:10], x = cast_data_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_c_ax1.title.set_text(labels[0])
h_c_ax2.title.set_text(labels[1])
p_c_ax3.title.set_text(labels[2])
d_c_ax4.title.set_text(labels[3])
 
plt.show()


df_tvshows_mixed_casts.drop(df_tvshows_mixed_casts.loc[df_tvshows_mixed_casts['Cast'] == "NA"].index, inplace = True)
# df_tvshows_mixed_casts = df_tvshows_mixed_casts[df_tvshows_mixed_casts.Cast != "NA"]
df_tvshows_mixed_casts.drop(df_tvshows_mixed_casts.loc[df_tvshows_mixed_casts['Number of Casts'] == 1].index, inplace = True)


df_tvshows_mixed_casts.head(5)


mixed_casts_count = df_tvshows_mixed_casts.groupby('Cast')['Title'].count()
mixed_casts_tvshows = df_tvshows_mixed_casts.groupby('Cast')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
mixed_casts_data_tvshows = pd.concat([mixed_casts_count, mixed_casts_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count', 'Cast' : 'Mixed Cast'})
mixed_casts_data_tvshows = mixed_casts_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)


mixed_casts_data_tvshows.head(5)


# Mixed Cast with TV Shows Counts - All Platforms Combined
mixed_casts_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)[:10]


df_mixed_casts_high_tvshows = mixed_casts_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_mixed_casts_high_tvshows = df_mixed_casts_high_tvshows.drop(['index'], axis = 1)
# filter = (mixed_casts_data_tvshows['TV Shows Count'] = =  (mixed_casts_data_tvshows['TV Shows Count'].max()))
# df_mixed_casts_high_tvshows = mixed_casts_data_tvshows[filter]
 
# highest_rated_tvshows = mixed_casts_data_tvshows.loc[mixed_casts_data_tvshows['TV Shows Count'].idxmax()]
 
print('\nMixed Cast with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_mixed_casts_high_tvshows.head(5)

Mixed Cast with Highest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_mixed_casts_high_tvshows['Mixed Cast'][:15],
             x = df_mixed_casts_high_tvshows['TV Shows Count'][:15], 
             color = df_mixed_casts_high_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Mixed Cast'},
             title  = 'TV Shows with Highest Number of Mixed Casts : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_mixed_casts_low_tvshows = mixed_casts_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_mixed_casts_low_tvshows = df_mixed_casts_low_tvshows.drop(['index'], axis = 1)
# filter = (mixed_casts_data_tvshows['TV Shows Count'] = =  (mixed_casts_data_tvshows['TV Shows Count'].min()))
# df_mixed_casts_low_tvshows = mixed_casts_data_tvshows[filter]
 
print('\nMixed Cast with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_mixed_casts_low_tvshows.head(5)

Mixed Cast with Lowest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_mixed_casts_low_tvshows['Mixed Cast'][:15],
             x = df_mixed_casts_low_tvshows['TV Shows Count'][:15], 
             color = df_mixed_casts_low_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Mixed Cast'},
             title  = 'TV Shows with Lowest Number of Mixed Casts : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_tvshows_casts['Cast'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see TV Shows from Total '{mixed_casts_data_tvshows['Mixed Cast'].unique().shape[0]}' Mixed Cast, They were Like this, \n
 
      {mixed_casts_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['Mixed Cast'].head(5).unique()} etc. \n
 
      The Mixed Cast with Highest TV Shows Count have '{mixed_casts_data_tvshows['TV Shows Count'].max()}' TV Shows Available is '{df_mixed_casts_high_tvshows['Mixed Cast'][0]}', &\n
      The Mixed Cast with Lowest TV Shows Count have '{mixed_casts_data_tvshows['TV Shows Count'].min()}' TV Shows Available is '{df_mixed_casts_low_tvshows['Mixed Cast'][0]}'
      ''')

      Total '4946' Titles are available on All Platforms, out of which

      You Can Choose to see TV Shows from Total '4546' Mixed Cast, They were Like this, 

 
      ['Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr'
 "Frank Grillo,Kiele Sanchez,Matt Lauria,Jonathan Tucker,Nick Jonas,Joanna Going,Juliette Jackson,Paul Walter Hauser,Joe Stevenson,Mac Brandt,Natalie Martinez,Levi Bowling,Juan Archuleta,Bryan Callen,Mike Beltran,Christie Philips,Kirk Acevedo,Lina Esco,Phil Abrams,Wendy Moniz-Grillo,Katherine Hughes,Jonathan Howard,Jamie Harris,Kenny Florian,Dean Stone,M.C. Gainey,Kim Robillard,Alisa Allapach,Jessica Szohr,Mark Consuelos,Roddy Rieger,Ahna O'Reilly,Bruce Davison,Ronnie Gene Blevins,Adam Shapiro,Mario Perez,Michael Stoyanov,Ishmel Sahid,Sean Quezada,Zuleikha Robinson,Obba Babatundé,Meaghan Rath,Michael Graziadei,Jai Rodriguez,Billy Lush,Patrick Fischler,Michael Mantell,Chloe Lanier,Frank Trigg,Michael Janashvili"
 "Michael Chiklis,Catherine Dent,Walton Goggins,Michael Jace,Jay Karnes,Benito Martinez,CCH Pounder,Cathy Cahlin Ryan,David Rees Snell,Kenny Johnson,David Marciano,Autumn Chiklis,Paula Garcés,Michele Hicks,Melanie Myers,Joel Rosenthal,Matt Corboy,Chaney Kley,Anthony Anderson,F.J. Rio,Nigel Gibbs,Glenn Close,Forest Whitaker,Laurie Holden,Camillia Monet,Brian White,Onahoua Rodriguez,Kenneth Colom,Michael Peña,Jack Weber,John Diehl,Anna Maria Horsford,Laurence Mason,Laura Harring,Ludwig Manukian,Linda Friedman,J. David Shanks,Aisha Hinds,Lucinda Jenney,Jamie Anne Allman,Alex O'Loughlin,Nicki Micheaux,Brent Roam,Monnae Michaell,Matt Gerald,Ben Hernandez Bray,Gareth Williams,Sticky Fingaz,Efrain Figueroa,RonReaco Lee"
 'Kevin McKidd,Ray Stevenson,Polly Walker,Kerry Condon,James Purefoy,Ian McNeice,Coral Amiga,Lindsay Duncan,Lidia Biondi,Tobias Menzies,Nicholas Woodeson,David Bamber,Chiara Mastalli,Manfredi Aliquo,Indira Varma,Suzanne Bertish,Max Pirkis,Lee Boardman,Esther Hall,Ciarán Hinds,Anna Fausta Primiano,Michael Nardone,Kenneth Cranham,Allen Leech,Guy Henry,Anna Francolini,Simon Woods,Zuleikha Robinson,Karl Johnson,Alex Wyndham,Paul Jesson,Camilla Rutherford,Daniel Cerqueira,Alessio Cuna,Lorcan Cranitch,Nigel Lindsay,Valery Usai,Lyndsey Marshal,Haydn Gwynne,Dominic Atherton,Julienne Liberto,Rick Warden,Amy Marston,Sara Pasqualone,Enzo Cilenti,Alan Williams,Kathryn Hunter,Alessio Di Cesare,Marco Pollak,Cosimo Fusco'
 'Charlie Day,Glenn Howerton,Rob McElhenney,Kaitlin Olson,Danny DeVito,Mary Elizabeth Ellis,David Hornsby,Artemis Pebdani,Lynne Marie Stewart,Sandy Martin,David Zdunich,Lance Barber,Andrew Friedman,Gregory Scott Cummins,Jimmi Simpson,Nate Mooney,Michael Naughton,Catherine Reitman,Travis Schuldt,Brian Unger,T.J. Hoban,Thesy Surface,Chad L. Coleman,John Ponzio,Bob Wiltfong,Brittany Daniel,Mario Di Donato,Anne Archer,Dave Foley,Shelly Desai,Jessica Collins,Mary Lynn Rajskub,David Gueriera,Nick Wechsler,Cormac Bluestone,Wil Garret,Lucy DeVito,Tom Bower,Stephen Collins,Jason Sudeikis,Aisha Hinds,Judy Greer,Dennis Hogan,Kyle Davis,Roddy Piper,Sasha Roiz,Peter Mackenzie,Zachary Knighton,Ray Auxias,Dennis Hart'] etc. 

 
      The Mixed Cast with Highest TV Shows Count have '4' TV Shows Available is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr', &

      The Mixed Cast with Lowest TV Shows Count have '1' TV Shows Available is 'Saloma Furlong,Anna,Naomi Kramer,Levi Shetler,Jan Edwards,Paul Edwards,Joe Keim,Bart Fletcher'


fig = px.pie(mixed_casts_data_tvshows[:10], names = 'Mixed Cast', values = 'TV Shows Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'TV Shows Count based on Mixed Cast')
fig.show()


# netflix_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_mixed_casts_tvshows = netflix_mixed_casts_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
netflix_mixed_casts_high_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_casts_high_tvshows = netflix_mixed_casts_high_tvshows.drop(['index'], axis = 1)
 
netflix_mixed_casts_low_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_mixed_casts_low_tvshows = netflix_mixed_casts_low_tvshows.drop(['index'], axis = 1)
 
netflix_mixed_casts_high_tvshows.head(5)


# hulu_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_mixed_casts_tvshows = hulu_mixed_casts_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
hulu_mixed_casts_high_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_casts_high_tvshows = hulu_mixed_casts_high_tvshows.drop(['index'], axis = 1)
 
hulu_mixed_casts_low_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_mixed_casts_low_tvshows = hulu_mixed_casts_low_tvshows.drop(['index'], axis = 1)
 
hulu_mixed_casts_high_tvshows.head(5)


# prime_video_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_mixed_casts_tvshows = prime_video_mixed_casts_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
 
prime_video_mixed_casts_high_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_casts_high_tvshows = prime_video_mixed_casts_high_tvshows.drop(['index'], axis = 1)
 
prime_video_mixed_casts_low_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_mixed_casts_low_tvshows = prime_video_mixed_casts_low_tvshows.drop(['index'], axis = 1)
 
prime_video_mixed_casts_high_tvshows.head(5)


# disney_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_mixed_casts_tvshows = disney_mixed_casts_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
 
disney_mixed_casts_high_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_casts_high_tvshows = disney_mixed_casts_high_tvshows.drop(['index'], axis = 1)
 
disney_mixed_casts_low_tvshows = df_mixed_casts_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_mixed_casts_low_tvshows = disney_mixed_casts_low_tvshows.drop(['index'], axis = 1)
 
disney_mixed_casts_high_tvshows.head(5)


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(mixed_casts_data_tvshows['TV Shows Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(mixed_casts_data_tvshows['TV Shows Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_casts_tvshows = netflix_mixed_casts_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

hulu_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_casts_tvshows = hulu_mixed_casts_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

prime_video_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_casts_tvshows = prime_video_mixed_casts_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)

disney_mixed_casts_tvshows = mixed_casts_data_tvshows[mixed_casts_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_casts_tvshows = disney_mixed_casts_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Cast TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(prime_video_mixed_casts_tvshows['Prime Video'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_mixed_casts_tvshows['Netflix'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_mixed_casts_tvshows['Hulu'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_mixed_casts_tvshows['Disney+'][:100], color = 'darkblue', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


print(f'''
      The Mixed Cast with Highest TV Shows Count Ever Got is '{df_mixed_casts_high_tvshows['Mixed Cast'][0]}' : '{df_mixed_casts_high_tvshows['TV Shows Count'].max()}'\n
      The Mixed Cast with Lowest TV Shows Count Ever Got is '{df_mixed_casts_low_tvshows['Mixed Cast'][0]}' : '{df_mixed_casts_low_tvshows['TV Shows Count'].min()}'\n
      
      The Mixed Cast with Highest TV Shows Count on 'Netflix' is '{netflix_mixed_casts_high_tvshows['Mixed Cast'][0]}' : '{netflix_mixed_casts_high_tvshows['Netflix'].max()}'\n
      The Mixed Cast with Lowest TV Shows Count on 'Netflix' is '{netflix_mixed_casts_low_tvshows['Mixed Cast'][0]}' : '{netflix_mixed_casts_low_tvshows['Netflix'].min()}'\n
      
      The Mixed Cast with Highest TV Shows Count on 'Hulu' is '{hulu_mixed_casts_high_tvshows['Mixed Cast'][0]}' : '{hulu_mixed_casts_high_tvshows['Hulu'].max()}'\n
      The Mixed Cast with Lowest TV Shows Count on 'Hulu' is '{hulu_mixed_casts_low_tvshows['Mixed Cast'][0]}' : '{hulu_mixed_casts_low_tvshows['Hulu'].min()}'\n
      
      The Mixed Cast with Highest TV Shows Count on 'Prime Video' is '{prime_video_mixed_casts_high_tvshows['Mixed Cast'][0]}' : '{prime_video_mixed_casts_high_tvshows['Prime Video'].max()}'\n
      The Mixed Cast with Lowest TV Shows Count on 'Prime Video' is '{prime_video_mixed_casts_low_tvshows['Mixed Cast'][0]}' : '{prime_video_mixed_casts_low_tvshows['Prime Video'].min()}'\n
      
      The Mixed Cast with Highest TV Shows Count on 'Disney+' is '{disney_mixed_casts_high_tvshows['Mixed Cast'][0]}' : '{disney_mixed_casts_high_tvshows['Disney+'].max()}'\n
      The Mixed Cast with Lowest TV Shows Count on 'Disney+' is '{disney_mixed_casts_low_tvshows['Mixed Cast'][0]}' : '{disney_mixed_casts_low_tvshows['Disney+'].min()}'\n 
      ''')

      The Mixed Cast with Highest TV Shows Count Ever Got is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr' : '4'

      The Mixed Cast with Lowest TV Shows Count Ever Got is 'Saloma Furlong,Anna,Naomi Kramer,Levi Shetler,Jan Edwards,Paul Edwards,Joe Keim,Bart Fletcher' : '1'

      
      The Mixed Cast with Highest TV Shows Count on 'Netflix' is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr' : '4'

      The Mixed Cast with Lowest TV Shows Count on 'Netflix' is 'Josh Friesen,Caitlynne Medrek,Nikki Rae Hallow,Nathan Hunt' : '0'

      
      The Mixed Cast with Highest TV Shows Count on 'Hulu' is 'Rebecca Romijn,Christian Kane,Lindy Booth,John Harlan Kim,John Larroquette,Noah Wyle,Matt Frewer,Lesley-Ann Brandt,David S. Lee,Rachel Nichols,Jane Curtin,Richard Cox,Vanessa Williams,Bob Newhart,Beth Riesgraf,Ryan Tresser,Keith Cox,Kendall Wells,Jon Bebe,Lex Damis,Tommy Daniels,Ciro Fusco,Timothy Eulich,Allison Kate,Tricia Helfer,Rene Auberjonois,Michelle N. Carter,Luke Cook,Kasha Kropinski,Drew Powell,Michael Trucco,Haley Webb,Kevin T. Williams,Alicia Witt,Lea Zawada,Sean Astin,Elizabeth Huffman,Eric Allan Kramer,Gia Carides,Richard Kind,Clara Lago,Rachael Perrell Fosket,Gloria Reuben,Samuel Roukin,Andrew Lewis Caldwell,Nora Dunn,T.J. Ramini,Sherri Saum,Tyler Mane,Razaaq Adoti' : '2'

      The Mixed Cast with Lowest TV Shows Count on 'Hulu' is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr' : '0'

      
      The Mixed Cast with Highest TV Shows Count on 'Prime Video' is 'Kate Mulgrew,Robert Beltran,Roxann Dawson,Robert Duncan McNeill,Ethan Phillips,Robert Picardo,Tim Russ,Garrett Wang,Tarik Ergin,Majel Barrett,Jeri Ryan,Jennifer Lien,Richard Sarstedt,Scarlett Pomers,Martha Hackett,Susan Henley,Manu Intiraymi,Alexander Enberg,Susan Lewis,Nancy Hower,Simon Billig,Josh Clark,David Keith Anderson,Dwight Schultz,Kurt Wetherill,Cody Wetherill,Raphael Sbarge,Anthony De Longis,Marley McClean,Vaughn Armstrong,Paul Eckstein,Steven Dennis,Mark Deakins,Richard Herd,Tom Virtue,Stan Ivar,Brad Dourif,Martin Rayner,Rob LaBelle,Larry Hankin,Jack Shearer,Rick Worthy,J. Paul Boehmer,Susanna Thompson,John de Lancie,John Gegenhuber,Susan Dalian,Deborah Levin,Lindsey Haun,Marina Sirtis' : '2'

      The Mixed Cast with Lowest TV Shows Count on 'Prime Video' is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr' : '0'

      
      The Mixed Cast with Highest TV Shows Count on 'Disney+' is 'Mandy Moore,Zachary Levi,Eden Espinosa,Paul F. Tompkins,James Monroe Iglehart,Clancy Brown,Jeffrey Ross,Sean Hayes,Jeremy Jordan,Steve Blum,Dee Bradley Baker,M.C. Gainey,Diedrich Bader,Julie Bowen,Jennifer Veal,Peter MacNicol,Vivian Vencer,Susanne Blakeslee,Charles Halford,Richard Kind,Gideon Emery,Jeffrey Tambor,Ruby Jay,Keith Ferguson,Jonathan Banks,Bruce Campbell,Kelly Hu,Adewale Akinnuoye-Agbaje,Donna Murphy,Mary Elizabeth McGlynn,Gavin Creel,Flula Borg,Hudson D'Andrea,Pat Carroll,Kevin Michael Richardson,Carol Kane,Ron Perlman,Britt Robertson,Bradley Whitford,Richard Steven Horvitz,Parker Bates,Brad Garrett,Natalie Palamides,Danny Trejo,Tony Amendola,Yvonne Strahovski,Timothy Dalton,Reg E. Cathey,Cassie Glow,Lance Henriksen' : '2'

      The Mixed Cast with Lowest TV Shows Count on 'Disney+' is 'Michela Luci,Nicolas Aqui,Jamie Watson,Eric Peterson,Dante Zee,Anna Claire Bartlam,Julie Lemieux,Cory Doran,Stephany Seki,Jonathan Tan,Addison Holley,Brandon McGibbon,T.J. McGibbon,Derek McGrath,Robert Knorr' : '0'


print(f'''
      Accross All Platforms the Average TV Shows Count of Mixed Cast is '{round(mixed_casts_data_tvshows['TV Shows Count'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Cast on 'Netflix' is '{round(netflix_mixed_casts_tvshows['Netflix'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Cast on 'Hulu' is '{round(hulu_mixed_casts_tvshows['Hulu'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Cast on 'Prime Video' is '{round(prime_video_mixed_casts_tvshows['Prime Video'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Cast on 'Disney+' is '{round(disney_mixed_casts_tvshows['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average TV Shows Count of Mixed Cast is '1.03'

      The Average TV Shows Count of Mixed Cast on 'Netflix' is '1.01'

      The Average TV Shows Count of Mixed Cast on 'Hulu' is '1.02'

      The Average TV Shows Count of Mixed Cast on 'Prime Video' is '1.01'

      The Average TV Shows Count of Mixed Cast on 'Disney+' is '1.01'


print(f'''
      Accross All Platforms Total Count of Mixed Cast is '{mixed_casts_data_tvshows['Mixed Cast'].unique().shape[0]}'\n
      Total Count of Mixed Cast on 'Netflix' is '{netflix_mixed_casts_tvshows['Mixed Cast'].unique().shape[0]}'\n
      Total Count of Mixed Cast on 'Hulu' is '{hulu_mixed_casts_tvshows['Mixed Cast'].unique().shape[0]}'\n
      Total Count of Mixed Cast on 'Prime Video' is '{prime_video_mixed_casts_tvshows['Mixed Cast'].unique().shape[0]}'\n
      Total Count of Mixed Cast on 'Disney+' is '{disney_mixed_casts_tvshows['Mixed Cast'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Mixed Cast is '4546'

      Total Count of Mixed Cast on 'Netflix' is '1698'

      Total Count of Mixed Cast on 'Hulu' is '1438'

      Total Count of Mixed Cast on 'Prime Video' is '1658'

      Total Count of Mixed Cast on 'Disney+' is '167'


plt.figure(figsize = (20, 5))
sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:5], y = mixed_casts_data_tvshows['Netflix'][:5], color = 'red')
sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:5], y = mixed_casts_data_tvshows['Hulu'][:5], color = 'lightgreen')
sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:5], y = mixed_casts_data_tvshows['Prime Video'][:5], color = 'lightblue')
sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:5], y = mixed_casts_data_tvshows['Disney+'][:5], color = 'darkblue')
plt.xlabel('Mixed Cast', fontsize = 15)
plt.ylabel('TV Shows Count', fontsize = 15)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_c_ax1 = sns.barplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_c_ax2 = sns.barplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_c_ax3 = sns.barplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_c_ax4 = sns.barplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_c_ax1.title.set_text(labels[0])
h_c_ax2.title.set_text(labels[1])
p_c_ax3.title.set_text(labels[2])
d_c_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_mc_ax1 = sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_mc_ax2 = sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_mc_ax3 = sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_mc_ax4 = sns.lineplot(x = mixed_casts_data_tvshows['Mixed Cast'][:10], y = mixed_casts_data_tvshows['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_mc_ax1.title.set_text(labels[0])
h_mc_ax2.title.set_text(labels[1])
p_mc_ax3.title.set_text(labels[2])
d_mc_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Cast  TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_mixed_casts_tvshows['Netflix'][:50], color = 'red', legend = True)
sns.kdeplot(hulu_mixed_casts_tvshows['Hulu'][:50], color = 'green', legend = True)
sns.kdeplot(prime_video_mixed_casts_tvshows['Prime Video'][:50], color = 'lightblue', legend = True)
sns.kdeplot(disney_mixed_casts_tvshows['Disney+'][:50], color = 'darkblue', legend = True)                                      

# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_mc_ax1 = sns.barplot(x = netflix_mixed_casts_tvshows['Mixed Cast'][:10], y = netflix_mixed_casts_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_mc_ax2 = sns.barplot(x = hulu_mixed_casts_tvshows['Mixed Cast'][:10], y = hulu_mixed_casts_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_mc_ax3 = sns.barplot(x = prime_video_mixed_casts_tvshows['Mixed Cast'][:10], y = prime_video_mixed_casts_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_mc_ax4 = sns.barplot(x = disney_mixed_casts_tvshows['Mixed Cast'][:10], y = disney_mixed_casts_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_mc_ax1.title.set_text(labels[0])
h_mc_ax2.title.set_text(labels[1])
p_mc_ax3.title.set_text(labels[2])
d_mc_ax4.title.set_text(labels[3])
 
plt.show()


fig = go.Figure(go.Funnel(y = mixed_casts_data_tvshows['Mixed Cast'][:10], x = mixed_casts_data_tvshows['TV Shows Count'][:10]))
fig.show()

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Seasons	Netflix	Prime Video	Disney+	Type
0	1	Snowpiercer	2013	18+	6.9	94%	NaN	Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso...	Action,Drama,Sci-Fi,Thriller	United States	English	Set seven years after the world has become a f...	60.0	tv series	3.0	1	0	0	1
1	2	Philadelphia	1993	13+	8.8	80%	NaN	Charlie Day,Glenn Howerton,Rob McElhenney,Kait...	Comedy	United States	English	The gang, 5 raging alcoholic, narcissists run ...	22.0	tv series	18.0	1	0	0	1
2	3	Roma	2018	18+	8.7	93%	NaN	Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ...	Action,Drama,History,Romance,War	United Kingdom,United States	English	In this British historical drama, the turbulen...	52.0	tv series	2.0	1	0	0	1
3	4	Amy	2015	18+	7.0	87%	NaN	Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma...	Drama	United States	English	A family drama focused on three generations of...	60.0	tv series	6.0	1	1	1	1
4	5	The Young Offenders	2016	NaN	8.0	100%	NaN	Alex Murphy,Chris Walley,Hilary Rose,Dominic M...	Comedy	United Kingdom,Ireland	English	NaN	30.0	tv series	3.0	1	0	0	1

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
count	5432.000000	5432.000000	5432.000000	5432.000000	5432.000000	5432.000000	5432.0
mean	2716.500000	2010.668446	0.341311	0.293999	0.403351	0.033689	1.0
std	1568.227662	11.726176	0.474193	0.455633	0.490615	0.180445	0.0
min	1.000000	1901.000000	0.000000	0.000000	0.000000	0.000000	1.0
25%	1358.750000	2009.000000	0.000000	0.000000	0.000000	0.000000	1.0
50%	2716.500000	2014.000000	0.000000	0.000000	0.000000	0.000000	1.0
75%	4074.250000	2017.000000	1.000000	1.000000	1.000000	0.000000	1.0
max	5432.000000	2020.000000	1.000000	1.000000	1.000000	1.000000	1.0

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
ID	1.000000	-0.031346	-0.646330	0.034293	0.441264	0.195409	NaN
Year	-0.031346	1.000000	0.222316	-0.065807	-0.198675	-0.022741	NaN
Netflix	-0.646330	0.222316	1.000000	-0.366515	-0.515086	-0.119344	NaN
Hulu	0.034293	-0.065807	-0.366515	1.000000	-0.377374	-0.075701	NaN
Prime Video	0.441264	-0.198675	-0.515086	-0.377374	1.000000	-0.151442	NaN
Disney+	0.195409	-0.022741	-0.119344	-0.075701	-0.151442	1.000000	NaN
Type	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	Mixed Cast	TV Shows Count	Netflix	Hulu	Prime Video
3062	Michela Luci,Nicolas Aqui,Jamie Watson,Eric Pe...	4	4	0	0
4231	Tom Waes,Frank Lammers,Manou Kersting,Anna Dri...	3	1	0	2
1450	Frank Grillo,Kiele Sanchez,Matt Lauria,Jonatha...	3	1	2	0
3017	Michael Chiklis,Catherine Dent,Walton Goggins,...	3	0	1	2
2499	Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ...	3	1	0	2

	Mixed Cast	TV Shows Count	Netflix	Hulu	Prime Video
3062	Michela Luci,Nicolas Aqui,Jamie Watson,Eric Pe...	4	4	0	0
1450	Frank Grillo,Kiele Sanchez,Matt Lauria,Jonatha...	3	1	2	0
3017	Michael Chiklis,Catherine Dent,Walton Goggins,...	3	0	1	2
2499	Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ...	3	1	0	2
739	Charlie Day,Glenn Howerton,Rob McElhenney,Kait...	3	1	1	1
4231	Tom Waes,Frank Lammers,Manou Kersting,Anna Dri...	3	1	0	2
4132	Telly Savalas,Dan Frazer,Kevin Dobson,George S...	2	0	2	0
4340	Victor Rasuk,Nathalie Kelley,Dan Bucatinsky,Da...	2	0	1	1
3782	Sanjeev Bhaskar,Jordan Long,Lewis Reeves,Nicol...	2	1	0	1
225	Anders W. Berthelsen,Zofia Wichlacz,Charlotte ...	2	0	0	2

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Netflix	Hulu	Prime Video	Type	Service Provider	Number of Casts
0	5191	The French Gun	2018	16	NA	NA	Wes Anderson	Saoirse Ronan,Frances McDormand,Adrien Brody,T...	Comedy,Drama,Romance	Germany,United States	...	103	tv series	NA	0	0	1	1	Prime Video	53
1	1	Snowpiercer	2013	18	6.9	94	NA	Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso...	Action,Drama,Sci-Fi,Thriller	United States	...	60	tv series	3	1	0	0	1	Netflix	50
2	2735	Dirty Sexy Money	2007	7	7.2	68	NA	Peter Krause,Donald Sutherland,William Baldwin...	Drama	United States	...	45	tv series	2	0	1	0	1	Hulu	50
3	2723	The Practice	1997	7	7.7	NA	NA	Steve Harris,Camryn Manheim,Michael Badalucco,...	Crime,Drama,Mystery,Romance,Thriller	United States	...	60	tv series	8	0	1	0	1	Hulu	50
4	2725	The Secret Life of the American Teenager	2008	16	5	NA	NA	Shailene Woodley,Ken Baumann,Daren Kagasoff,Me...	Comedy,Drama,Family,Romance	United States	...	43	tv series	5	0	1	0	1	Hulu	50

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Netflix	Hulu	Prime Video	Disney+	Type	Service Provider	Number of Casts
0	3656	Struggle Meals	2017	0	8.7	NA	NA	Frank Celenza	Comedy	United States	...	12	tv series	7	0	1	1	0	1	Prime Video	1
1	4897	Troy in Train Town	2016	NR	NA	NA	NA	June Yoon	Animation,Family	NA	...	20	tv series	NA	0	0	1	0	1	Prime Video	1
2	437	KAALA (Malayalam)	2018	NR	NA	NA	Anuraj	Malavika Krishnadas	Drama	India	...	22	tv series	NA	0	0	1	0	1	Prime Video	1
3	5318	Disney Gallery / Star Wars: The Mandalorian	2020	7	8.5	100	Josiah Swanson	Josiah Swanson	Talk-Show	NA	...	NA	tv series	NA	0	0	0	1	1	Disney+	1
4	2109	Everyday Miracles: The Genius of Sofas, Stocki...	2014	0	7.4	NA	NA	Mark Miodownik	Documentary	United Kingdom	...	NA	tv series	1	1	0	0	0	1	Netflix	1

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Hulu	Disney+	Type	Service Provider	Number of Casts
0	2704	K.C. Undercover	2015	7	6.2	NA	NA	Zendaya,Veronica Dunne,Kamil McFadden,Trinitee...	Action,Comedy,Drama,Family	United States	...	30	tv series	3	1	1	1	Disney+	50
1	2768	The Incredible Dr. Pol	2011	7	8.6	NA	NA	Jan Pol,Ari Rubin,Diane Pol,Charles Pol,Brenda...	Documentary,Reality-TV	United States	...	44	tv series	18	1	1	1	Disney+	50
2	2572	X-Men: Evolution	2000	7	7.9	NA	NA	Kirby Morrow,Venus Terzo,David Kaye,Brad Swail...	Animation,Action,Drama,Fantasy,Romance,Sci-Fi,...	United States,Canada	...	23	tv series	4	1	1	1	Disney+	50
3	2574	Good Luck Charlie	2010	0	7	NA	NA	Bridgit Mendler,Leigh-Allyn Baker,Bradley Stev...	Comedy,Drama,Family	United States	...	22	tv series	4	1	1	1	Disney+	50
4	2960	Doc McStuffins	2012	0	6.7	NA	NA	Lara Jill Miller,Loretta Devine,Robbie Rist,Je...	Animation,Short,Family,Fantasy,Music,Musical	United States,Ireland	...	11	tv series	5	1	1	1	Disney+	50

	Cast	TV Shows Count	Netflix	Hulu	Prime Video	Disney+
24021	Dee Bradley Baker	94	24	30	11	38
35047	Grey Griffin	87	26	34	15	22
69189	Monica Rial	86	15	74	12	0
53697	Kevin Michael Richardson	77	21	26	8	28
31868	Fred Tatasciore	75	30	23	9	20
59455	Luci Christian	71	14	55	15	0
42855	Jeff Bennett	68	17	25	7	23
93904	Tom Kenny	64	15	30	10	14
93613	Todd Haberkorn	62	30	41	4	0
46461	John DiMaggio	61	21	26	4	15

	Cast	TV Shows Count	Netflix	Hulu	Prime Video
0	Pamela West	1	0	0	1
1	David Allister	1	0	0	1
2	David Altshuler	1	0	0	1
3	David Alvarado	1	1	0	0
4	David Andreoli	1	0	1	0

	Cast	TV Shows Count	Netflix	Hulu	Prime Video	Disney+
0	Keith Silverstein	48	35	14	2	3
1	Cherami Leigh	52	34	24	3	0
2	Cristina Valenzuela	46	33	13	7	1
3	Erika Harlacher	41	32	9	3	0
4	Kyle McCarley	34	31	8	3	0

	Cast	TV Shows Count	Netflix	Hulu	Prime Video
0	Monica Rial	86	15	74	12
1	Luci Christian	71	14	55	15
2	Ian Sinclair	45	2	43	4
3	Colleen Clinkenbeard	44	8	42	1
4	Todd Haberkorn	62	30	41	4

	Cast	TV Shows Count	Netflix	Hulu	Prime Video	Disney+
0	Grey Griffin	87	26	34	15	22
1	Frank Welker	54	10	15	15	18
2	Luci Christian	71	14	55	15	0
3	John Swasey	45	10	32	15	0
4	Monica Rial	86	15	74	12	0

	Cast	TV Shows Count	Netflix	Hulu	Prime Video	Disney+
0	Dee Bradley Baker	94	24	30	11	38
1	Kevin Michael Richardson	77	21	26	8	28
2	Jim Cummings	55	9	14	8	25
3	Jeff Bennett	68	17	25	7	23
4	Grey Griffin	87	26	34	15	22

	Mixed Cast	TV Shows Count	Netflix	Hulu	Prime Video
0	Saloma Furlong,Anna,Naomi Kramer,Levi Shetler,...	1	0	0	1
1	Aden Young,Abigail Spencer,J. Smith-Cameron,Ad...	1	1	0	0
2	Aden Young,Sam Trammell,Simone Kessell,Milly A...	1	1	0	0
3	Adewale Akinnuoye-Agbaje,Angela Trimbur,John B...	1	0	1	0
4	Aditi Sudhir Pohankar,Vijay Varma,Vishwas Kini...	1	1	0	0

	Mixed Cast	TV Shows Count	Netflix	Hulu
0	Michela Luci,Nicolas Aqui,Jamie Watson,Eric Pe...	4	4	0
1	Lee Min-Ho,Park Shin-Hye,Woo-bin Kim,Kim Ji-Wo...	2	2	0
2	Ben Diskin,Shinnosuke Mitsushima,Michelle Ruff...	2	2	1
3	Jonah Hill,Emma Stone,Sonoya Mizuno,Justin The...	2	2	0
4	Alessandro Borghi,Giacomo Ferrara,Filippo Nigr...	2	2	0

	Mixed Cast	TV Shows Count	Hulu	Prime Video
0	Rebecca Romijn,Christian Kane,Lindy Booth,John...	2	2	0
1	Michael Strahan,Sara Haines,Keke Palmer,Kenya ...	2	2	0
2	Randall Park,Constance Wu,Hudson Yang,Forrest ...	2	2	0
3	Katie Gray,Crispin Freeman,Victoria Harwood,Ra...	2	2	0
4	Anna Maxwell Martin,Denis Lawson,Carey Mulliga...	2	2	1

	Mixed Cast	TV Shows Count	Netflix	Hulu	Prime Video
0	Kate Mulgrew,Robert Beltran,Roxann Dawson,Robe...	2	1	1	2
1	Jack Whitehall,Rosie Perez,Christian Ochoa,Cha...	2	0	0	2
2	Bill Cosby,Phylicia Rashad,Keshia Knight Pulli...	2	0	0	2
3	Maryke Hendrikse,Stephanie Komure,Marlo Flanag...	2	0	0	2
4	Helen Mirren,Hugh Dancy,Toby Jones,Patrick Mal...	2	0	0	2

	Mixed Cast	TV Shows Count	Disney+
0	Mandy Moore,Zachary Levi,Eden Espinosa,Paul F....	2	2
1	David Tennant,Ben Schwartz,Danny Pudi,Bobby Mo...	2	2
2	Blake Anderson,Tyree Brown,David Cowgill,Jenni...	1	1
3	Rich Collins,Scott Durbin,David Poche,Wendy Ca...	1	1
4	Angelica Bolognesi Bonacini,Jim Cummings,Chloë...	1	1